Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     وزن
    -0.08
    Banner
    -0.07
    apore
    -0.06
    .DoesNotExist
    -0.06
    AZE
    -0.06
    ıyor
    -0.06
    .banner
    -0.06
    DEF
    -0.06
    .qt
    -0.06
    .bam
    -0.06
    POSITIVE LOGITS
    озя
    0.07
    �性
    0.06
    464
    0.06
     Optimization
    0.06
     erad
    0.06
     전세가
    0.06
     unjust
    0.06
    ishes
    0.06
     corrobor
    0.06
    -str
    0.06
    Act Density 0.057%

    No Known Activations